COLA: Contextualized Commonsense Causal Reasoning from the Causal Inference Perspective
This work addresses a challenging task in natural language processing for improving contextualized reasoning, but it appears incremental as it builds on prior commonsense causation work by adding context.
The paper tackles the problem of detecting commonsense causal relations between events by introducing a new task that incorporates context, and proposes a zero-shot framework called COLA, which achieves more accurate detection than baselines in experiments.
Detecting commonsense causal relations (causation) between events has long been an essential yet challenging task. Given that events are complicated, an event may have different causes under various contexts. Thus, exploiting context plays an essential role in detecting causal relations. Meanwhile, previous works about commonsense causation only consider two events and ignore their context, simplifying the task formulation. This paper proposes a new task to detect commonsense causation between two events in an event sequence (i.e., context), called contextualized commonsense causal reasoning. We also design a zero-shot framework: COLA (Contextualized Commonsense Causality Reasoner) to solve the task from the causal inference perspective. This framework obtains rich incidental supervision from temporality and balances covariates from multiple timestamps to remove confounding effects. Our extensive experiments show that COLA can detect commonsense causality more accurately than baselines.